Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data with a focus on statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estine
    -0.81
    hood
    -0.74
    erate
    -0.72
    uscript
    -0.69
    pton
    -0.69
    friend
    -0.65
    ened
    -0.64
    istically
    -0.64
    ying
    -0.64
    ledged
    -0.63
    POSITIVE LOGITS
     ILCS
    1.01
    mph
    0.88
     entrants
    0.80
    lbs
    0.76
     chars
    0.74
    ANT
    0.73
     MPH
    0.72
     lbs
    0.72
     mph
    0.71
    ants
    0.70
    Act Density 0.082%

    No Known Activations